aboutsummaryrefslogtreecommitdiffstats
path: root/target/linux/generic/backport-5.4/080-wireguard-0031-crypto-arm-curve25519-wire-up-NEON-implementation.patch
blob: e1ca6af64d2f67e13400b669bffa44a453ee87d5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Fri, 8 Nov 2019 13:22:38 +0100
Subject: [PATCH] crypto: arm/curve25519 - wire up NEON implementation

commit d8f1308a025fc7e00414194ed742d5f05a21e13c upstream.

This ports the SUPERCOP implementation for usage in kernel space. In
addition to the usual header, macro, and style changes required for
kernel space, it makes a few small changes to the code:

  - The stack alignment is relaxed to 16 bytes.
  - Superfluous mov statements have been removed.
  - ldr for constants has been replaced with movw.
  - ldreq has been replaced with moveq.
  - The str epilogue has been made more idiomatic.
  - SIMD registers are not pushed and popped at the beginning and end.
  - The prologue and epilogue have been made idiomatic.
  - A hole has been removed from the stack, saving 32 bytes.
  - We write-back the base register whenever possible for vld1.8.
  - Some multiplications have been reordered for better A7 performance.

There are more opportunities for cleanup, since this code is from qhasm,
which doesn't always do the most opportune thing. But even prior to
extensive hand optimizations, this code delivers significant performance
improvements (given in get_cycles() per call):

		      ----------- -------------
	             | generic C | this commit |
	 ------------ ----------- -------------
	| Cortex-A7  |     49136 |       22395 |
	 ------------ ----------- -------------
	| Cortex-A17 |     17326 |        4983 |
	 ------------ ----------- -------------

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
[ardb: - move to arch/arm/crypto
       - wire into lib/crypto framework
       - implement crypto API KPP hooks ]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 arch/arm/crypto/Kconfig           |   6 +
 arch/arm/crypto/Makefile          |   2 +
 arch/arm/crypto/curve25519-core.S | 347 +++++++++++++-----------------
 arch/arm/crypto/curve25519-glue.c | 127 +++++++++++
 4 files changed, 287 insertions(+), 195 deletions(-)
 create mode 100644 arch/arm/crypto/curve25519-glue.c

--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -143,4 +143,10 @@ config CRYPTO_NHPOLY1305_NEON
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_NHPOLY1305
 
+config CRYPTO_CURVE25519_NEON
+	tristate "NEON accelerated Curve25519 scalar multiplication library"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_LIB_CURVE25519_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+
 endif
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha51
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
 obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
+obj-$(CONFIG_CRYPTO_CURVE25519_NEON) += curve25519-neon.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -38,6 +39,7 @@ chacha-neon-y := chacha-scalar-core.o ch
 chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
 poly1305-arm-y := poly1305-core.o poly1305-glue.o
 nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
+curve25519-neon-y := curve25519-core.o curve25519-glue.o
 
 ifdef REGENERATE_ARM_CRYPTO
 quiet_cmd_perl = PERL    $@
--- a/arch/arm/crypto/curve25519-core.S
+++ b/arch/arm/crypto/curve25519-core.S
@@ -1,43 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /*
- * Public domain code from Daniel J. Bernstein and Peter Schwabe, from
- * SUPERCOP's curve25519/neon2/scalarmult.s.
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
  */
 
-.fpu neon
+#include <linux/linkage.h>
+
 .text
+.fpu neon
+.arch armv7-a
 .align 4
-.global _crypto_scalarmult_curve25519_neon2
-.global crypto_scalarmult_curve25519_neon2
-.type _crypto_scalarmult_curve25519_neon2 STT_FUNC
-.type crypto_scalarmult_curve25519_neon2 STT_FUNC
-	_crypto_scalarmult_curve25519_neon2:
-	crypto_scalarmult_curve25519_neon2:
-	vpush		{q4, q5, q6, q7}
-	mov		r12, sp
-	sub		sp, sp, #736
-	and		sp, sp, #0xffffffe0
-	strd		r4, [sp, #0]
-	strd		r6, [sp, #8]
-	strd		r8, [sp, #16]
-	strd		r10, [sp, #24]
-	str		r12, [sp, #480]
-	str		r14, [sp, #484]
-	mov		r0, r0
-	mov		r1, r1
-	mov		r2, r2
-	add		r3, sp, #32
-	ldr		r4, =0
-	ldr		r5, =254
+
+ENTRY(curve25519_neon)
+	push		{r4-r11, lr}
+	mov		ip, sp
+	sub		r3, sp, #704
+	and		r3, r3, #0xfffffff0
+	mov		sp, r3
+	movw		r4, #0
+	movw		r5, #254
 	vmov.i32	q0, #1
 	vshr.u64	q1, q0, #7
 	vshr.u64	q0, q0, #8
 	vmov.i32	d4, #19
 	vmov.i32	d5, #38
-	add		r6, sp, #512
-	vst1.8		{d2-d3}, [r6, : 128]
-	add		r6, sp, #528
-	vst1.8		{d0-d1}, [r6, : 128]
-	add		r6, sp, #544
+	add		r6, sp, #480
+	vst1.8		{d2-d3}, [r6, : 128]!
+	vst1.8		{d0-d1}, [r6, : 128]!
 	vst1.8		{d4-d5}, [r6, : 128]
 	add		r6, r3, #0
 	vmov.i32	q2, #0
@@ -45,12 +37,12 @@
 	vst1.8		{d4-d5}, [r6, : 128]!
 	vst1.8		d4, [r6, : 64]
 	add		r6, r3, #0
-	ldr		r7, =960
+	movw		r7, #960
 	sub		r7, r7, #2
 	neg		r7, r7
 	sub		r7, r7, r7, LSL #7
 	str		r7, [r6]
-	add		r6, sp, #704
+	add		r6, sp, #672
 	vld1.8		{d4-d5}, [r1]!
 	vld1.8		{d6-d7}, [r1]
 	vst1.8		{d4-d5}, [r6, : 128]!
@@ -212,15 +204,15 @@
 	vst1.8		{d0-d1}, [r6, : 128]!
 	vst1.8		{d2-d3}, [r6, : 128]!
 	vst1.8		d4, [r6, : 64]
-._mainloop:
+.Lmainloop:
 	mov		r2, r5, LSR #3
 	and		r6, r5, #7
 	ldrb		r2, [r1, r2]
 	mov		r2, r2, LSR r6
 	and		r2, r2, #1
-	str		r5, [sp, #488]
+	str		r5, [sp, #456]
 	eor		r4, r4, r2
-	str		r2, [sp, #492]
+	str		r2, [sp, #460]
 	neg		r2, r4
 	add		r4, r3, #96
 	add		r5, r3, #192
@@ -291,7 +283,7 @@
 	vsub.i32	q0, q1, q3
 	vst1.8		d4, [r4, : 64]
 	vst1.8		d0, [r6, : 64]
-	add		r2, sp, #544
+	add		r2, sp, #512
 	add		r4, r3, #96
 	add		r5, r3, #144
 	vld1.8		{d0-d1}, [r2, : 128]
@@ -361,14 +353,13 @@
 	vmlal.s32	q0, d12, d8
 	vmlal.s32	q0, d13, d17
 	vmlal.s32	q0, d6, d6
-	add		r2, sp, #512
-	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d18-d19}, [r2, : 128]!
 	vmull.s32	q3, d16, d7
 	vmlal.s32	q3, d10, d15
 	vmlal.s32	q3, d11, d14
 	vmlal.s32	q3, d12, d9
 	vmlal.s32	q3, d13, d8
-	add		r2, sp, #528
 	vld1.8		{d8-d9}, [r2, : 128]
 	vadd.i64	q5, q12, q9
 	vadd.i64	q6, q15, q9
@@ -502,22 +493,19 @@
 	vadd.i32	q5, q5, q0
 	vtrn.32		q11, q14
 	vadd.i32	q6, q6, q3
-	add		r2, sp, #560
+	add		r2, sp, #528
 	vadd.i32	q10, q10, q2
 	vtrn.32		d24, d25
-	vst1.8		{d12-d13}, [r2, : 128]
+	vst1.8		{d12-d13}, [r2, : 128]!
 	vshl.i32	q6, q13, #1
-	add		r2, sp, #576
-	vst1.8		{d20-d21}, [r2, : 128]
+	vst1.8		{d20-d21}, [r2, : 128]!
 	vshl.i32	q10, q14, #1
-	add		r2, sp, #592
-	vst1.8		{d12-d13}, [r2, : 128]
+	vst1.8		{d12-d13}, [r2, : 128]!
 	vshl.i32	q15, q12, #1
 	vadd.i32	q8, q8, q4
 	vext.32		d10, d31, d30, #0
 	vadd.i32	q7, q7, q1
-	add		r2, sp, #608
-	vst1.8		{d16-d17}, [r2, : 128]
+	vst1.8		{d16-d17}, [r2, : 128]!
 	vmull.s32	q8, d18, d5
 	vmlal.s32	q8, d26, d4
 	vmlal.s32	q8, d19, d9
@@ -528,8 +516,7 @@
 	vmlal.s32	q8, d29, d1
 	vmlal.s32	q8, d24, d6
 	vmlal.s32	q8, d25, d0
-	add		r2, sp, #624
-	vst1.8		{d14-d15}, [r2, : 128]
+	vst1.8		{d14-d15}, [r2, : 128]!
 	vmull.s32	q2, d18, d4
 	vmlal.s32	q2, d12, d9
 	vmlal.s32	q2, d13, d8
@@ -537,8 +524,7 @@
 	vmlal.s32	q2, d22, d2
 	vmlal.s32	q2, d23, d1
 	vmlal.s32	q2, d24, d0
-	add		r2, sp, #640
-	vst1.8		{d20-d21}, [r2, : 128]
+	vst1.8		{d20-d21}, [r2, : 128]!
 	vmull.s32	q7, d18, d9
 	vmlal.s32	q7, d26, d3
 	vmlal.s32	q7, d19, d8
@@ -547,14 +533,12 @@
 	vmlal.s32	q7, d28, d1
 	vmlal.s32	q7, d23, d6
 	vmlal.s32	q7, d29, d0
-	add		r2, sp, #656
-	vst1.8		{d10-d11}, [r2, : 128]
+	vst1.8		{d10-d11}, [r2, : 128]!
 	vmull.s32	q5, d18, d3
 	vmlal.s32	q5, d19, d2
 	vmlal.s32	q5, d22, d1
 	vmlal.s32	q5, d23, d0
 	vmlal.s32	q5, d12, d8
-	add		r2, sp, #672
 	vst1.8		{d16-d17}, [r2, : 128]
 	vmull.s32	q4, d18, d8
 	vmlal.s32	q4, d26, d2
@@ -566,7 +550,7 @@
 	vmlal.s32	q8, d26, d1
 	vmlal.s32	q8, d19, d6
 	vmlal.s32	q8, d27, d0
-	add		r2, sp, #576
+	add		r2, sp, #544
 	vld1.8		{d20-d21}, [r2, : 128]
 	vmlal.s32	q7, d24, d21
 	vmlal.s32	q7, d25, d20
@@ -575,32 +559,30 @@
 	vmlal.s32	q8, d22, d21
 	vmlal.s32	q8, d28, d20
 	vmlal.s32	q5, d24, d20
-	add		r2, sp, #576
 	vst1.8		{d14-d15}, [r2, : 128]
 	vmull.s32	q7, d18, d6
 	vmlal.s32	q7, d26, d0
-	add		r2, sp, #656
+	add		r2, sp, #624
 	vld1.8		{d30-d31}, [r2, : 128]
 	vmlal.s32	q2, d30, d21
 	vmlal.s32	q7, d19, d21
 	vmlal.s32	q7, d27, d20
-	add		r2, sp, #624
+	add		r2, sp, #592
 	vld1.8		{d26-d27}, [r2, : 128]
 	vmlal.s32	q4, d25, d27
 	vmlal.s32	q8, d29, d27
 	vmlal.s32	q8, d25, d26
 	vmlal.s32	q7, d28, d27
 	vmlal.s32	q7, d29, d26
-	add		r2, sp, #608
+	add		r2, sp, #576
 	vld1.8		{d28-d29}, [r2, : 128]
 	vmlal.s32	q4, d24, d29
 	vmlal.s32	q8, d23, d29
 	vmlal.s32	q8, d24, d28
 	vmlal.s32	q7, d22, d29
 	vmlal.s32	q7, d23, d28
-	add		r2, sp, #608
 	vst1.8		{d8-d9}, [r2, : 128]
-	add		r2, sp, #560
+	add		r2, sp, #528
 	vld1.8		{d8-d9}, [r2, : 128]
 	vmlal.s32	q7, d24, d9
 	vmlal.s32	q7, d25, d31
@@ -621,36 +603,36 @@
 	vmlal.s32	q0, d23, d26
 	vmlal.s32	q0, d24, d31
 	vmlal.s32	q0, d19, d20
-	add		r2, sp, #640
+	add		r2, sp, #608
 	vld1.8		{d18-d19}, [r2, : 128]
 	vmlal.s32	q2, d18, d7
-	vmlal.s32	q2, d19, d6
 	vmlal.s32	q5, d18, d6
-	vmlal.s32	q5, d19, d21
 	vmlal.s32	q1, d18, d21
-	vmlal.s32	q1, d19, d29
 	vmlal.s32	q0, d18, d28
-	vmlal.s32	q0, d19, d9
 	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
 	vmlal.s32	q6, d19, d28
-	add		r2, sp, #592
+	add		r2, sp, #560
 	vld1.8		{d18-d19}, [r2, : 128]
-	add		r2, sp, #512
+	add		r2, sp, #480
 	vld1.8		{d22-d23}, [r2, : 128]
 	vmlal.s32	q5, d19, d7
 	vmlal.s32	q0, d18, d21
 	vmlal.s32	q0, d19, d29
 	vmlal.s32	q6, d18, d6
-	add		r2, sp, #528
+	add		r2, sp, #496
 	vld1.8		{d6-d7}, [r2, : 128]
 	vmlal.s32	q6, d19, d21
-	add		r2, sp, #576
+	add		r2, sp, #544
 	vld1.8		{d18-d19}, [r2, : 128]
 	vmlal.s32	q0, d30, d8
-	add		r2, sp, #672
+	add		r2, sp, #640
 	vld1.8		{d20-d21}, [r2, : 128]
 	vmlal.s32	q5, d30, d29
-	add		r2, sp, #608
+	add		r2, sp, #576
 	vld1.8		{d24-d25}, [r2, : 128]
 	vmlal.s32	q1, d30, d28
 	vadd.i64	q13, q0, q11
@@ -823,22 +805,19 @@
 	vadd.i32	q5, q5, q0
 	vtrn.32		q11, q14
 	vadd.i32	q6, q6, q3
-	add		r2, sp, #560
+	add		r2, sp, #528
 	vadd.i32	q10, q10, q2
 	vtrn.32		d24, d25
-	vst1.8		{d12-d13}, [r2, : 128]
+	vst1.8		{d12-d13}, [r2, : 128]!
 	vshl.i32	q6, q13, #1
-	add		r2, sp, #576
-	vst1.8		{d20-d21}, [r2, : 128]
+	vst1.8		{d20-d21}, [r2, : 128]!
 	vshl.i32	q10, q14, #1
-	add		r2, sp, #592
-	vst1.8		{d12-d13}, [r2, : 128]
+	vst1.8		{d12-d13}, [r2, : 128]!
 	vshl.i32	q15, q12, #1
 	vadd.i32	q8, q8, q4
 	vext.32		d10, d31, d30, #0
 	vadd.i32	q7, q7, q1
-	add		r2, sp, #608
-	vst1.8		{d16-d17}, [r2, : 128]
+	vst1.8		{d16-d17}, [r2, : 128]!
 	vmull.s32	q8, d18, d5
 	vmlal.s32	q8, d26, d4
 	vmlal.s32	q8, d19, d9
@@ -849,8 +828,7 @@
 	vmlal.s32	q8, d29, d1
 	vmlal.s32	q8, d24, d6
 	vmlal.s32	q8, d25, d0
-	add		r2, sp, #624
-	vst1.8		{d14-d15}, [r2, : 128]
+	vst1.8		{d14-d15}, [r2, : 128]!
 	vmull.s32	q2, d18, d4
 	vmlal.s32	q2, d12, d9
 	vmlal.s32	q2, d13, d8
@@ -858,8 +836,7 @@
 	vmlal.s32	q2, d22, d2
 	vmlal.s32	q2, d23, d1
 	vmlal.s32	q2, d24, d0
-	add		r2, sp, #640
-	vst1.8		{d20-d21}, [r2, : 128]
+	vst1.8		{d20-d21}, [r2, : 128]!
 	vmull.s32	q7, d18, d9
 	vmlal.s32	q7, d26, d3
 	vmlal.s32	q7, d19, d8
@@ -868,15 +845,13 @@
 	vmlal.s32	q7, d28, d1
 	vmlal.s32	q7, d23, d6
 	vmlal.s32	q7, d29, d0
-	add		r2, sp, #656
-	vst1.8		{d10-d11}, [r2, : 128]
+	vst1.8		{d10-d11}, [r2, : 128]!
 	vmull.s32	q5, d18, d3
 	vmlal.s32	q5, d19, d2
 	vmlal.s32	q5, d22, d1
 	vmlal.s32	q5, d23, d0
 	vmlal.s32	q5, d12, d8
-	add		r2, sp, #672
-	vst1.8		{d16-d17}, [r2, : 128]
+	vst1.8		{d16-d17}, [r2, : 128]!
 	vmull.s32	q4, d18, d8
 	vmlal.s32	q4, d26, d2
 	vmlal.s32	q4, d19, d7
@@ -887,7 +862,7 @@
 	vmlal.s32	q8, d26, d1
 	vmlal.s32	q8, d19, d6
 	vmlal.s32	q8, d27, d0
-	add		r2, sp, #576
+	add		r2, sp, #544
 	vld1.8		{d20-d21}, [r2, : 128]
 	vmlal.s32	q7, d24, d21
 	vmlal.s32	q7, d25, d20
@@ -896,32 +871,30 @@
 	vmlal.s32	q8, d22, d21
 	vmlal.s32	q8, d28, d20
 	vmlal.s32	q5, d24, d20
-	add		r2, sp, #576
 	vst1.8		{d14-d15}, [r2, : 128]
 	vmull.s32	q7, d18, d6
 	vmlal.s32	q7, d26, d0
-	add		r2, sp, #656
+	add		r2, sp, #624
 	vld1.8		{d30-d31}, [r2, : 128]
 	vmlal.s32	q2, d30, d21
 	vmlal.s32	q7, d19, d21
 	vmlal.s32	q7, d27, d20
-	add		r2, sp, #624
+	add		r2, sp, #592
 	vld1.8		{d26-d27}, [r2, : 128]
 	vmlal.s32	q4, d25, d27
 	vmlal.s32	q8, d29, d27
 	vmlal.s32	q8, d25, d26
 	vmlal.s32	q7, d28, d27
 	vmlal.s32	q7, d29, d26
-	add		r2, sp, #608
+	add		r2, sp, #576
 	vld1.8		{d28-d29}, [r2, : 128]
 	vmlal.s32	q4, d24, d29
 	vmlal.s32	q8, d23, d29
 	vmlal.s32	q8, d24, d28
 	vmlal.s32	q7, d22, d29
 	vmlal.s32	q7, d23, d28
-	add		r2, sp, #608
 	vst1.8		{d8-d9}, [r2, : 128]
-	add		r2, sp, #560
+	add		r2, sp, #528
 	vld1.8		{d8-d9}, [r2, : 128]
 	vmlal.s32	q7, d24, d9
 	vmlal.s32	q7, d25, d31
@@ -942,36 +915,36 @@
 	vmlal.s32	q0, d23, d26
 	vmlal.s32	q0, d24, d31
 	vmlal.s32	q0, d19, d20
-	add		r2, sp, #640
+	add		r2, sp, #608
 	vld1.8		{d18-d19}, [r2, : 128]
 	vmlal.s32	q2, d18, d7
-	vmlal.s32	q2, d19, d6
 	vmlal.s32	q5, d18, d6
-	vmlal.s32	q5, d19, d21
 	vmlal.s32	q1, d18, d21
-	vmlal.s32	q1, d19, d29
 	vmlal.s32	q0, d18, d28
-	vmlal.s32	q0, d19, d9
 	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
 	vmlal.s32	q6, d19, d28
-	add		r2, sp, #592
+	add		r2, sp, #560
 	vld1.8		{d18-d19}, [r2, : 128]
-	add		r2, sp, #512
+	add		r2, sp, #480
 	vld1.8		{d22-d23}, [r2, : 128]
 	vmlal.s32	q5, d19, d7
 	vmlal.s32	q0, d18, d21
 	vmlal.s32	q0, d19, d29
 	vmlal.s32	q6, d18, d6
-	add		r2, sp, #528
+	add		r2, sp, #496
 	vld1.8		{d6-d7}, [r2, : 128]
 	vmlal.s32	q6, d19, d21
-	add		r2, sp, #576
+	add		r2, sp, #544
 	vld1.8		{d18-d19}, [r2, : 128]
 	vmlal.s32	q0, d30, d8
-	add		r2, sp, #672
+	add		r2, sp, #640
 	vld1.8		{d20-d21}, [r2, : 128]
 	vmlal.s32	q5, d30, d29
-	add		r2, sp, #608
+	add		r2, sp, #576
 	vld1.8		{d24-d25}, [r2, : 128]
 	vmlal.s32	q1, d30, d28
 	vadd.i64	q13, q0, q11
@@ -1069,7 +1042,7 @@
 	sub		r4, r4, #24
 	vst1.8		d0, [r2, : 64]
 	vst1.8		d1, [r4, : 64]
-	add		r2, sp, #544
+	add		r2, sp, #512
 	add		r4, r3, #144
 	add		r5, r3, #192
 	vld1.8		{d0-d1}, [r2, : 128]
@@ -1139,14 +1112,13 @@
 	vmlal.s32	q0, d12, d8
 	vmlal.s32	q0, d13, d17
 	vmlal.s32	q0, d6, d6
-	add		r2, sp, #512
-	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d18-d19}, [r2, : 128]!
 	vmull.s32	q3, d16, d7
 	vmlal.s32	q3, d10, d15
 	vmlal.s32	q3, d11, d14
 	vmlal.s32	q3, d12, d9
 	vmlal.s32	q3, d13, d8
-	add		r2, sp, #528
 	vld1.8		{d8-d9}, [r2, : 128]
 	vadd.i64	q5, q12, q9
 	vadd.i64	q6, q15, q9
@@ -1295,22 +1267,19 @@
 	vadd.i32	q5, q5, q0
 	vtrn.32		q11, q14
 	vadd.i32	q6, q6, q3
-	add		r2, sp, #560
+	add		r2, sp, #528
 	vadd.i32	q10, q10, q2
 	vtrn.32		d24, d25
-	vst1.8		{d12-d13}, [r2, : 128]
+	vst1.8		{d12-d13}, [r2, : 128]!
 	vshl.i32	q6, q13, #1
-	add		r2, sp, #576
-	vst1.8		{d20-d21}, [r2, : 128]
+	vst1.8		{d20-d21}, [r2, : 128]!
 	vshl.i32	q10, q14, #1
-	add		r2, sp, #592
-	vst1.8		{d12-d13}, [r2, : 128]
+	vst1.8		{d12-d13}, [r2, : 128]!
 	vshl.i32	q15, q12, #1
 	vadd.i32	q8, q8, q4
 	vext.32		d10, d31, d30, #0
 	vadd.i32	q7, q7, q1
-	add		r2, sp, #608
-	vst1.8		{d16-d17}, [r2, : 128]
+	vst1.8		{d16-d17}, [r2, : 128]!
 	vmull.s32	q8, d18, d5
 	vmlal.s32	q8, d26, d4
 	vmlal.s32	q8, d19, d9
@@ -1321,8 +1290,7 @@
 	vmlal.s32	q8, d29, d1
 	vmlal.s32	q8, d24, d6
 	vmlal.s32	q8, d25, d0
-	add		r2, sp, #624
-	vst1.8		{d14-d15}, [r2, : 128]
+	vst1.8		{d14-d15}, [r2, : 128]!
 	vmull.s32	q2, d18, d4
 	vmlal.s32	q2, d12, d9
 	vmlal.s32	q2, d13, d8
@@ -1330,8 +1298,7 @@
 	vmlal.s32	q2, d22, d2
 	vmlal.s32	q2, d23, d1
 	vmlal.s32	q2, d24, d0
-	add		r2, sp, #640
-	vst1.8		{d20-d21}, [r2, : 128]
+	vst1.8		{d20-d21}, [r2, : 128]!
 	vmull.s32	q7, d18, d9
 	vmlal.s32	q7, d26, d3
 	vmlal.s32	q7, d19, d8
@@ -1340,15 +1307,13 @@
 	vmlal.s32	q7, d28, d1
 	vmlal.s32	q7, d23, d6
 	vmlal.s32	q7, d29, d0
-	add		r2, sp, #656
-	vst1.8		{d10-d11}, [r2, : 128]
+	vst1.8		{d10-d11}, [r2, : 128]!
 	vmull.s32	q5, d18, d3
 	vmlal.s32	q5, d19, d2
 	vmlal.s32	q5, d22, d1
 	vmlal.s32	q5, d23, d0
 	vmlal.s32	q5, d12, d8
-	add		r2, sp, #672
-	vst1.8		{d16-d17}, [r2, : 128]
+	vst1.8		{d16-d17}, [r2, : 128]!
 	vmull.s32	q4, d18, d8
 	vmlal.s32	q4, d26, d2
 	vmlal.s32	q4, d19, d7
@@ -1359,7 +1324,7 @@
 	vmlal.s32	q8, d26, d1
 	vmlal.s32	q8, d19, d6
 	vmlal.s32	q8, d27, d0
-	add		r2, sp, #576
+	add		r2, sp, #544
 	vld1.8		{d20-d21}, [r2, : 128]
 	vmlal.s32	q7, d24, d21
 	vmlal.s32	q7, d25, d20
@@ -1368,32 +1333,30 @@
 	vmlal.s32	q8, d22, d21
 	vmlal.s32	q8, d28, d20
 	vmlal.s32	q5, d24, d20
-	add		r2, sp, #576
 	vst1.8		{d14-d15}, [r2, : 128]
 	vmull.s32	q7, d18, d6
 	vmlal.s32	q7, d26, d0
-	add		r2, sp, #656
+	add		r2, sp, #624
 	vld1.8		{d30-d31}, [r2, : 128]
 	vmlal.s32	q2, d30, d21
 	vmlal.s32	q7, d19, d21
 	vmlal.s32	q7, d27, d20
-	add		r2, sp, #624
+	add		r2, sp, #592
 	vld1.8		{d26-d27}, [r2, : 128]
 	vmlal.s32	q4, d25, d27
 	vmlal.s32	q8, d29, d27
 	vmlal.s32	q8, d25, d26
 	vmlal.s32	q7, d28, d27
 	vmlal.s32	q7, d29, d26
-	add		r2, sp, #608
+	add		r2, sp, #576
 	vld1.8		{d28-d29}, [r2, : 128]
 	vmlal.s32	q4, d24, d29
 	vmlal.s32	q8, d23, d29
 	vmlal.s32	q8, d24, d28
 	vmlal.s32	q7, d22, d29
 	vmlal.s32	q7, d23, d28
-	add		r2, sp, #608
 	vst1.8		{d8-d9}, [r2, : 128]
-	add		r2, sp, #560
+	add		r2, sp, #528
 	vld1.8		{d8-d9}, [r2, : 128]
 	vmlal.s32	q7, d24, d9
 	vmlal.s32	q7, d25, d31
@@ -1414,36 +1377,36 @@
 	vmlal.s32	q0, d23, d26
 	vmlal.s32	q0, d24, d31
 	vmlal.s32	q0, d19, d20
-	add		r2, sp, #640
+	add		r2, sp, #608
 	vld1.8		{d18-d19}, [r2, : 128]
 	vmlal.s32	q2, d18, d7
-	vmlal.s32	q2, d19, d6
 	vmlal.s32	q5, d18, d6
-	vmlal.s32	q5, d19, d21
 	vmlal.s32	q1, d18, d21
-	vmlal.s32	q1, d19, d29
 	vmlal.s32	q0, d18, d28
-	vmlal.s32	q0, d19, d9
 	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
 	vmlal.s32	q6, d19, d28
-	add		r2, sp, #592
+	add		r2, sp, #560
 	vld1.8		{d18-d19}, [r2, : 128]
-	add		r2, sp, #512
+	add		r2, sp, #480
 	vld1.8		{d22-d23}, [r2, : 128]
 	vmlal.s32	q5, d19, d7
 	vmlal.s32	q0, d18, d21
 	vmlal.s32	q0, d19, d29
 	vmlal.s32	q6, d18, d6
-	add		r2, sp, #528
+	add		r2, sp, #496
 	vld1.8		{d6-d7}, [r2, : 128]
 	vmlal.s32	q6, d19, d21
-	add		r2, sp, #576
+	add		r2, sp, #544
 	vld1.8		{d18-d19}, [r2, : 128]
 	vmlal.s32	q0, d30, d8
-	add		r2, sp, #672
+	add		r2, sp, #640
 	vld1.8		{d20-d21}, [r2, : 128]
 	vmlal.s32	q5, d30, d29
-	add		r2, sp, #608
+	add		r2, sp, #576
 	vld1.8		{d24-d25}, [r2, : 128]
 	vmlal.s32	q1, d30, d28
 	vadd.i64	q13, q0, q11
@@ -1541,10 +1504,10 @@
 	sub		r4, r4, #24
 	vst1.8		d0, [r2, : 64]
 	vst1.8		d1, [r4, : 64]
-	ldr		r2, [sp, #488]
-	ldr		r4, [sp, #492]
+	ldr		r2, [sp, #456]
+	ldr		r4, [sp, #460]
 	subs		r5, r2, #1
-	bge		._mainloop
+	bge		.Lmainloop
 	add		r1, r3, #144
 	add		r2, r3, #336
 	vld1.8		{d0-d1}, [r1, : 128]!
@@ -1553,41 +1516,41 @@
 	vst1.8		{d0-d1}, [r2, : 128]!
 	vst1.8		{d2-d3}, [r2, : 128]!
 	vst1.8		d4, [r2, : 64]
-	ldr		r1, =0
-._invertloop:
+	movw		r1, #0
+.Linvertloop:
 	add		r2, r3, #144
-	ldr		r4, =0
-	ldr		r5, =2
+	movw		r4, #0
+	movw		r5, #2
 	cmp		r1, #1
-	ldreq		r5, =1
+	moveq		r5, #1
 	addeq		r2, r3, #336
 	addeq		r4, r3, #48
 	cmp		r1, #2
-	ldreq		r5, =1
+	moveq		r5, #1
 	addeq		r2, r3, #48
 	cmp		r1, #3
-	ldreq		r5, =5
+	moveq		r5, #5
 	addeq		r4, r3, #336
 	cmp		r1, #4
-	ldreq		r5, =10
+	moveq		r5, #10
 	cmp		r1, #5
-	ldreq		r5, =20
+	moveq		r5, #20
 	cmp		r1, #6
-	ldreq		r5, =10
+	moveq		r5, #10
 	addeq		r2, r3, #336
 	addeq		r4, r3, #336
 	cmp		r1, #7
-	ldreq		r5, =50
+	moveq		r5, #50
 	cmp		r1, #8
-	ldreq		r5, =100
+	moveq		r5, #100
 	cmp		r1, #9
-	ldreq		r5, =50
+	moveq		r5, #50
 	addeq		r2, r3, #336
 	cmp		r1, #10
-	ldreq		r5, =5
+	moveq		r5, #5
 	addeq		r2, r3, #48
 	cmp		r1, #11
-	ldreq		r5, =0
+	moveq		r5, #0
 	addeq		r2, r3, #96
 	add		r6, r3, #144
 	add		r7, r3, #288
@@ -1598,8 +1561,8 @@
 	vst1.8		{d2-d3}, [r7, : 128]!
 	vst1.8		d4, [r7, : 64]
 	cmp		r5, #0
-	beq		._skipsquaringloop
-._squaringloop:
+	beq		.Lskipsquaringloop
+.Lsquaringloop:
 	add		r6, r3, #288
 	add		r7, r3, #288
 	add		r8, r3, #288
@@ -1611,7 +1574,7 @@
 	vld1.8		{d6-d7}, [r7, : 128]!
 	vld1.8		{d9}, [r7, : 64]
 	vld1.8		{d10-d11}, [r6, : 128]!
-	add		r7, sp, #416
+	add		r7, sp, #384
 	vld1.8		{d12-d13}, [r6, : 128]!
 	vmul.i32	q7, q2, q0
 	vld1.8		{d8}, [r6, : 64]
@@ -1726,7 +1689,7 @@
 	vext.32		d10, d6, d6, #0
 	vmov.i32	q1, #0xffffffff
 	vshl.i64	q4, q1, #25
-	add		r7, sp, #512
+	add		r7, sp, #480
 	vld1.8		{d14-d15}, [r7, : 128]
 	vadd.i64	q9, q2, q7
 	vshl.i64	q1, q1, #26
@@ -1735,7 +1698,7 @@
 	vadd.i64	q5, q5, q10
 	vand		q9, q9, q1
 	vld1.8		{d16}, [r6, : 64]!
-	add		r6, sp, #528
+	add		r6, sp, #496
 	vld1.8		{d20-d21}, [r6, : 128]
 	vadd.i64	q11, q5, q10
 	vsub.i64	q2, q2, q9
@@ -1789,8 +1752,8 @@
 	sub		r6, r6, #32
 	vst1.8		d4, [r6, : 64]
 	subs		r5, r5, #1
-	bhi		._squaringloop
-._skipsquaringloop:
+	bhi		.Lsquaringloop
+.Lskipsquaringloop:
 	mov		r2, r2
 	add		r5, r3, #288
 	add		r6, r3, #144
@@ -1802,7 +1765,7 @@
 	vld1.8		{d6-d7}, [r5, : 128]!
 	vld1.8		{d9}, [r5, : 64]
 	vld1.8		{d10-d11}, [r2, : 128]!
-	add		r5, sp, #416
+	add		r5, sp, #384
 	vld1.8		{d12-d13}, [r2, : 128]!
 	vmul.i32	q7, q2, q0
 	vld1.8		{d8}, [r2, : 64]
@@ -1917,7 +1880,7 @@
 	vext.32		d10, d6, d6, #0
 	vmov.i32	q1, #0xffffffff
 	vshl.i64	q4, q1, #25
-	add		r5, sp, #512
+	add		r5, sp, #480
 	vld1.8		{d14-d15}, [r5, : 128]
 	vadd.i64	q9, q2, q7
 	vshl.i64	q1, q1, #26
@@ -1926,7 +1889,7 @@
 	vadd.i64	q5, q5, q10
 	vand		q9, q9, q1
 	vld1.8		{d16}, [r2, : 64]!
-	add		r2, sp, #528
+	add		r2, sp, #496
 	vld1.8		{d20-d21}, [r2, : 128]
 	vadd.i64	q11, q5, q10
 	vsub.i64	q2, q2, q9
@@ -1980,7 +1943,7 @@
 	sub		r2, r2, #32
 	vst1.8		d4, [r2, : 64]
 	cmp		r4, #0
-	beq		._skippostcopy
+	beq		.Lskippostcopy
 	add		r2, r3, #144
 	mov		r4, r4
 	vld1.8		{d0-d1}, [r2, : 128]!
@@ -1989,9 +1952,9 @@
 	vst1.8		{d0-d1}, [r4, : 128]!
 	vst1.8		{d2-d3}, [r4, : 128]!
 	vst1.8		d4, [r4, : 64]
-._skippostcopy:
+.Lskippostcopy:
 	cmp		r1, #1
-	bne		._skipfinalcopy
+	bne		.Lskipfinalcopy
 	add		r2, r3, #288
 	add		r4, r3, #144
 	vld1.8		{d0-d1}, [r2, : 128]!
@@ -2000,10 +1963,10 @@
 	vst1.8		{d0-d1}, [r4, : 128]!
 	vst1.8		{d2-d3}, [r4, : 128]!
 	vst1.8		d4, [r4, : 64]
-._skipfinalcopy:
+.Lskipfinalcopy:
 	add		r1, r1, #1
 	cmp		r1, #12
-	blo		._invertloop
+	blo		.Linvertloop
 	add		r1, r3, #144
 	ldr		r2, [r1], #4
 	ldr		r3, [r1], #4
@@ -2085,21 +2048,15 @@
 	add		r8, r8, r10, LSL #12
 	mov		r9, r10, LSR #20
 	add		r1, r9, r1, LSL #6
-	str		r2, [r0], #4
-	str		r3, [r0], #4
-	str		r4, [r0], #4
-	str		r5, [r0], #4
-	str		r6, [r0], #4
-	str		r7, [r0], #4
-	str		r8, [r0], #4
-	str		r1, [r0]
-	ldrd		r4, [sp, #0]
-	ldrd		r6, [sp, #8]
-	ldrd		r8, [sp, #16]
-	ldrd		r10, [sp, #24]
-	ldr		r12, [sp, #480]
-	ldr		r14, [sp, #484]
-	ldr		r0, =0
-	mov		sp, r12
-	vpop		{q4, q5, q6, q7}
-	bx		lr
+	str		r2, [r0]
+	str		r3, [r0, #4]
+	str		r4, [r0, #8]
+	str		r5, [r0, #12]
+	str		r6, [r0, #16]
+	str		r7, [r0, #20]
+	str		r8, [r0, #24]
+	str		r1, [r0, #28]
+	movw		r0, #0
+	mov		sp, ip
+	pop		{r4-r11, pc}
+ENDPROC(curve25519_neon)
--- /dev/null
+++ b/arch/arm/crypto/curve25519-glue.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/internal/simd.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <crypto/curve25519.h>
+
+asmlinkage void curve25519_neon(u8 mypublic[CURVE25519_KEY_SIZE],
+				const u8 secret[CURVE25519_KEY_SIZE],
+				const u8 basepoint[CURVE25519_KEY_SIZE]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void curve25519_arch(u8 out[CURVE25519_KEY_SIZE],
+		     const u8 scalar[CURVE25519_KEY_SIZE],
+		     const u8 point[CURVE25519_KEY_SIZE])
+{
+	if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
+		kernel_neon_begin();
+		curve25519_neon(out, scalar, point);
+		kernel_neon_end();
+	} else {
+		curve25519_generic(out, scalar, point);
+	}
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+				 unsigned int len)
+{
+	u8 *secret = kpp_tfm_ctx(tfm);
+
+	if (!len)
+		curve25519_generate_secret(secret);
+	else if (len == CURVE25519_KEY_SIZE &&
+		 crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+		memcpy(secret, buf, CURVE25519_KEY_SIZE);
+	else
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 public_key[CURVE25519_KEY_SIZE];
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+	u8 const *bp;
+
+	if (req->src) {
+		copied = sg_copy_to_buffer(req->src,
+					   sg_nents_for_len(req->src,
+							    CURVE25519_KEY_SIZE),
+					   public_key, CURVE25519_KEY_SIZE);
+		if (copied != CURVE25519_KEY_SIZE)
+			return -EINVAL;
+		bp = public_key;
+	} else {
+		bp = curve25519_base_point;
+	}
+
+	curve25519_arch(buf, secret, bp);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+	return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+	.base.cra_name		= "curve25519",
+	.base.cra_driver_name	= "curve25519-neon",
+	.base.cra_priority	= 200,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_ctxsize	= CURVE25519_KEY_SIZE,
+
+	.set_secret		= curve25519_set_secret,
+	.generate_public_key	= curve25519_compute_value,
+	.compute_shared_secret	= curve25519_compute_value,
+	.max_size		= curve25519_max_size,
+};
+
+static int __init mod_init(void)
+{
+	if (elf_hwcap & HWCAP_NEON) {
+		static_branch_enable(&have_neon);
+		return crypto_register_kpp(&curve25519_alg);
+	}
+	return 0;
+}
+
+static void __exit mod_exit(void)
+{
+	if (elf_hwcap & HWCAP_NEON)
+		crypto_unregister_kpp(&curve25519_alg);
+}
+
+module_init(mod_init);
+module_exit(mod_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-neon");
+MODULE_LICENSE("GPL v2");